Novelty-based Multiobjectivization
Contact: mouret@isir.upmc.fr
Reference
Mouret, J.-B. (2009). Novelty-based Multiobjectivization. In Exploring New Horizons in Evolutionary Design of Robots (IROS Workshop).
Abstract
Novelty search is a recent and promising approach to evolve neuro-controllers, especially to drive robots. The main idea is to maximize the novelty of behaviors instead of the efficiency. However, abandoning the efficiency objective(s) may be too radical in many contexts. In this paper, a Pareto-based multi-objective evolutionary algorithm is employed to reconcile novelty search with objective-based optimization by following a multiobjectivization process. Several multiobjectivizations based on behavioral novelty and on behavioral diversity are compared on a maze navigation task. Results show that the multiobjectivizations is better at fine-tuning behaviors than basic novelty search while keeping a comparable number of iterations to converge.
Link to the paper
Associated source code
Reproduction of the experiment
This paper & experiment mainly confirms the results published in : J. Lehman and K. Stanley (2008). Exploiting open-endedness to solve problems through the search for novelty, in Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems
None yet.
For each person wishing to distribute its code reproducing (or not) the results of the paper, please provide the following data: